Llama 3 8B Spaetzle V13: benchmark results

Provider: Meta. Access: Open.

Aggregate Rating 1450 ± 33, rank #3766 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU68.06Accuracy (%) (5-shot)90.4
Open LLM Leaderboard v1 - GSM8K67.1Accuracy (%) (5-shot)83
Open LLM Leaderboard v1 - ARC Challenge68.69Normalized accuracy (%) (25-shot)81
Open LLM Leaderboard v1 - TruthfulQA MC259.43MC2 (%) (0-shot)73.7
Open LLM Leaderboard v1 - HellaSwag85.05Normalized accuracy (%) (10-shot)71.3
Open LLM Leaderboard v1 - WinoGrande79.24Accuracy (%) (5-shot)68.1

Interactive version: theaggregate.ai/model?slug=llama-3-8b-spaetzle-v13 · How It Works · Data refreshed daily, snapshot 2026-11-08.